Tidak Ada Deskripsi

NNNNAI b394ffdffd Updated 4 tahun lalu
crop_224 3ee304b0e1 update 4 tahun lalu
data 01a8d6d0a6 init 4 tahun lalu
demo_file 29f9bb6d0e Demo image or video 4 tahun lalu
doc 5fc482cf65 update 4 tahun lalu
insightface_func 6e5ee6a3f6 Insightface: used to detect and align faces 4 tahun lalu
models 01a8d6d0a6 init 4 tahun lalu
options b394ffdffd Updated 4 tahun lalu
output 3ee304b0e1 update 4 tahun lalu
simswaplogo b394ffdffd Updated 4 tahun lalu
util b394ffdffd Updated 4 tahun lalu
.gitattributes a0dab0c7b1 Initial commit 4 tahun lalu
.gitignore a887c06799 update 4 tahun lalu
LICENSE 2d4c69790f Update LICENSE 4 tahun lalu
README.md 5fc482cf65 update 4 tahun lalu
test_one_image.py b394ffdffd Updated 4 tahun lalu

README.md

SimSwap: An Efficient Framework For High Fidelity Face Swapping

Proceedings of the 28th ACM International Conference on Multimedia

The official repository with Pytorch

Currently, only the test code is available, and training scripts are coming soon simswaplogo

[Arxiv paper]

[ACM DOI paper]

[Google Drive Paper link]

[Baidu Drive Paper link] Password: ummt

video2 video3 video4 video5

Results

Results1

Results2

Video

High-quality videos can be found in the link below:

[Mama(video) 1080p]

[Google Drive link for video 1]

[Google Drive link for video 2]

[Google Drive link for video 3]

[Baidu Drive link for video] Password: b26n

[Online Video]

Dependencies

  • python3.6+
  • pytorch1.5+
  • torchvision
  • opencv
  • pillow
  • numpy

Usage

To test the pretrained model

python test_one_image.py --isTrain false  --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/

--name refers to the SimSwap training logs name.

Pretrained model

Usage

There are two archive files in the drive: checkpoints.zip and arcface_checkpoint.tar

  • Copy the arcface_checkpoint.tar into ./arcface_model
  • Unzip checkpoints.zip, place it in the root dir ./

[Google Drive]

[Baidu Drive] Password: jd2v

To cite our paper

@inproceedings{DBLP:conf/mm/ChenCNG20,
  author    = {Renwang Chen and
               Xuanhong Chen and
               Bingbing Ni and
               Yanhao Ge},
  title     = {SimSwap: An Efficient Framework For High Fidelity Face Swapping},
  booktitle = {{MM} '20: The 28th {ACM} International Conference on Multimedia},
  pages     = {2003--2011},
  publisher = {{ACM}},
  year      = {2020},
  url       = {https://doi.org/10.1145/3394171.3413630},
  doi       = {10.1145/3394171.3413630},
  timestamp = {Thu, 15 Oct 2020 16:32:08 +0200},
  biburl    = {https://dblp.org/rec/conf/mm/ChenCNG20.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Related Projects

Please visit our another ACMMM2020 high-quality style transfer project

logo

title

Learn about our other projects [RainNet];

[Sketch Generation];

[CooGAN];

[Knowledge Style Transfer];

[SimSwap];

[ASMA-GAN];

[SNGAN-Projection-pytorch]

[Pretrained_VGG19].